ClawHub
Back to skill

Security audit

钉钉日报自动提交

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed DingTalk daily-report automation guide, but users should understand it can send work-log content on a schedule and clear the local submitted text.

Before installing, confirm the DingTalk recipients, app credentials, cron schedule, and whether submitted work text is archived anywhere before it is cleared. The reviewed artifact is documentation-only and does not include the referenced script or config files.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly automates submission of daily work logs and supports configurable recipients, but the description section does not clearly warn users that work-log content and recipient identifiers will be transmitted to DingTalk on a schedule. This can lead to unintended disclosure of sensitive work information or personal identifiers if users enable the skill without understanding the automatic outbound data flow.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill states that submitted content is automatically cleared after submission, but this behavior is described as a feature rather than a clear warning about destructive data handling. Users may lose important records if they do not realize the local work log will be erased after an automated submission, especially in a scheduled workflow where the deletion may occur without immediate visibility.

Content

No source excerpt is available for this finding.